Recently, due to information overflow, users are not being able to find the information they actually want fast enough. So, a variety of information processing methods have been suggested to resolve this problem. And this study intends to discuss espe...
Recently, due to information overflow, users are not being able to find the information they actually want fast enough. So, a variety of information processing methods have been suggested to resolve this problem. And this study intends to discuss especially the one using emotional filter among various information processing methods. Since the emotional filter which is the term defined in this study is not yet settled, so it was used as the common name for emotion filtration or emotional recommendation from previous studies, which performs the same function as emotion filter.
The existing music recommendation service on the web has a weak point that it makes the user feel bored by recommending songs only with similar feeling of the same genre, because music is classified by tune, melody, atmosphere and genre before recommendation.
The service using emotion filter, suggested in this study, recommends the song and lyrics appropriate to the current emotional state of the user by abstracting emotional words that could reflect the sensitivity of human and then search the words within lyrics to match in order to overcome the weak point of the existing service.
This study starts where the current emotional status for the user is being input. As for the range to choose, there are the seven representatives of emotion which are, love, separation, joy, sorrow-gloom, happiness-lonesome, and anger. And each of these seven representative emotions has the twenty subordinate vocabularies. The emotional words which is the subordinate words to the representative emotion can be derived, using the relations of synonymy and equivalent on WordNet, from words in Korean dictionary which could express humans’ emotion well. As the service receives input of user’s emotion, it matches the emotional words appropriate for the emotion input with the lyrics, and ranks the lyrics in the order of priority, so that it recommends the song and it lyrics to the user. After this, the user will rate the recommended song and its lyrics with five-point scale descried as ‘good’, ‘a little good’, ‘medium’, ‘so- so’, ‘bad’.
To compare the service proposed in this study with the existing one, the existing music recommendation service and the newly suggested service were set up as the control group and the experimental group respectively and then examined. For examination, the lyrics in 100 songs were obtained from the popular song list of October, and then experiment was conducted under the assumption that the user wanted to be recommended songs about ‘love’ The result of the words extraction for the sensitive word “Love” produced 20 words including love, lover, sweetheart, affection, pretty, beautiful, lovely, loving, precious, beloved, and etc. for use. As for the control group, the song ‘when I fall in love’ was used in song recommendation service of M-net, and all the songs provided were the same genre, the ballad. And this kind of result would highly like to make the user bored while listening to music. In contrast, the lyrics recommendation service using emotional words, as observed in experiment, recommends songs from various genres when recommending songs regarding love.
As a result, the service proposed in this study was confirmed that it recommended various genre of songs distinctively different from the unified result from the existing service, thus also was verified its superiority.